How to use the wordfreq.top_n_list function in wordfreq
To help you get started, we’ve selected a few wordfreq examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
OWASP / passfault / wordlists / wordlist scripts / wordlists.py View on Github 
from wordfreq import word_frequency
from wordfreq import zipf_frequency
from wordfreq import top_n_list
import matplotlib.pyplot as plt
dest = "../src/org/owasp/passfault/wordlists/"
de = top_n_list('de', 1e5, wordlist='large')
en = top_n_list('en', 1e5, wordlist='large')
es = top_n_list('es', 1e5, wordlist='large')
fr = top_n_list('fr', 1e5, wordlist='large')
it = top_n_list('it', 1e5, wordlist='large')
nl = top_n_list('nl', 1e5, wordlist='large')
pt = top_n_list('pt', 1e5, wordlist='large')
#---------------------------------------------------------------
dePopular = open(dest + '/dePopular.words', 'w')
deLongTail = open(dest + '/deLongTail.words', 'w')
integral100 = 0
for i in range(len(de)):
integral100 += word_frequency(de[i], 'de', wordlist='large')
print(integral100)
integral80 = 0
for i in range(len(de)):
integral80 += word_frequency(de[i], 'de', wordlist='large')#Written by Bernardo Rodrigues (bernardoaraujor@gmail.com)
#Based on Luminoso Insight's wordfreq module (https://github.com/LuminosoInsight/wordfreq/)
from wordfreq import word_frequency
from wordfreq import zipf_frequency
from wordfreq import top_n_list
#import matplotlib.pyplot as plt
dest = "./wordlists/"
ar = top_n_list('ar', 1e5, wordlist='large')
de = top_n_list('de', 1e5, wordlist='large')
en = top_n_list('en', 1e5, wordlist='large')
es = top_n_list('es', 1e5, wordlist='large')
fi = top_n_list('fi', 1e5)
fr = top_n_list('fr', 1e5, wordlist='large')
hi = top_n_list('hi', 1e5)
it = top_n_list('it', 1e5, wordlist='large')
ja = top_n_list('ja', 1e5)
nl = top_n_list('nl', 1e5, wordlist='large')
sv = top_n_list('sv', 1e5)
pt = top_n_list('pt', 1e5, wordlist='large')
zh = top_n_list('zh', 1e5)
#---------------------------------------------------------------
arPopular = open(dest + '/arPopular.txt', 'w')
arLongTail = open(dest + '/arLongTail.txt', 'w')"""
A quick script to output the top N words (1000 for now) in each language.
You can send the output to a file and diff it to see changes between wordfreq
versions.
"""
import wordfreq
N = 1000
if __name__ == '__main__':
for lang in sorted(wordfreq.available_languages()):
for word in wordfreq.top_n_list(lang, 1000):
print('{}\t{}'.format(lang, word))#Written by Bernardo Rodrigues (bernardoaraujor@gmail.com)
#Based on Luminoso Insight's wordfreq module (https://github.com/LuminosoInsight/wordfreq/)
from wordfreq import word_frequency
from wordfreq import zipf_frequency
from wordfreq import top_n_list
#import matplotlib.pyplot as plt
dest = "./wordlists/"
ar = top_n_list('ar', 1e5, wordlist='large')
de = top_n_list('de', 1e5, wordlist='large')
en = top_n_list('en', 1e5, wordlist='large')
es = top_n_list('es', 1e5, wordlist='large')
fi = top_n_list('fi', 1e5)
fr = top_n_list('fr', 1e5, wordlist='large')
hi = top_n_list('hi', 1e5)
it = top_n_list('it', 1e5, wordlist='large')
ja = top_n_list('ja', 1e5)
nl = top_n_list('nl', 1e5, wordlist='large')
sv = top_n_list('sv', 1e5)
pt = top_n_list('pt', 1e5, wordlist='large')
zh = top_n_list('zh', 1e5)
#---------------------------------------------------------------
arPopular = open(dest + '/arPopular.txt', 'w')
arLongTail = open(dest + '/arLongTail.txt', 'w')from wordfreq import word_frequency
from wordfreq import zipf_frequency
from wordfreq import top_n_list
import matplotlib.pyplot as plt
dest = "../src/org/owasp/passfault/wordlists/"
de = top_n_list('de', 1e5, wordlist='large')
en = top_n_list('en', 1e5, wordlist='large')
es = top_n_list('es', 1e5, wordlist='large')
fr = top_n_list('fr', 1e5, wordlist='large')
it = top_n_list('it', 1e5, wordlist='large')
nl = top_n_list('nl', 1e5, wordlist='large')
pt = top_n_list('pt', 1e5, wordlist='large')
#---------------------------------------------------------------
dePopular = open(dest + '/dePopular.words', 'w')
deLongTail = open(dest + '/deLongTail.words', 'w')
integral100 = 0
for i in range(len(de)):
integral100 += word_frequency(de[i], 'de', wordlist='large')
print(integral100)
integral80 = 0
for i in range(len(de)):from wordfreq import word_frequency
from wordfreq import zipf_frequency
from wordfreq import top_n_list
import matplotlib.pyplot as plt
dest = "../src/org/owasp/passfault/wordlists/"
de = top_n_list('de', 1e5, wordlist='large')
en = top_n_list('en', 1e5, wordlist='large')
es = top_n_list('es', 1e5, wordlist='large')
fr = top_n_list('fr', 1e5, wordlist='large')
it = top_n_list('it', 1e5, wordlist='large')
nl = top_n_list('nl', 1e5, wordlist='large')
pt = top_n_list('pt', 1e5, wordlist='large')
#---------------------------------------------------------------
dePopular = open(dest + '/dePopular.words', 'w')
deLongTail = open(dest + '/deLongTail.words', 'w')
integral100 = 0
for i in range(len(de)):
integral100 += word_frequency(de[i], 'de', wordlist='large')
print(integral100)
integral80 = 0
for i in range(len(de)):
integral80 += word_frequency(de[i], 'de', wordlist='large')
if (integral80 <= 0.80*integral100):
dePopular.write(de[i] + '\n')from wordfreq import zipf_frequency
from wordfreq import top_n_list
#import matplotlib.pyplot as plt
dest = "./wordlists/"
ar = top_n_list('ar', 1e5, wordlist='large')
de = top_n_list('de', 1e5, wordlist='large')
en = top_n_list('en', 1e5, wordlist='large')
es = top_n_list('es', 1e5, wordlist='large')
fi = top_n_list('fi', 1e5)
fr = top_n_list('fr', 1e5, wordlist='large')
hi = top_n_list('hi', 1e5)
it = top_n_list('it', 1e5, wordlist='large')
ja = top_n_list('ja', 1e5)
nl = top_n_list('nl', 1e5, wordlist='large')
sv = top_n_list('sv', 1e5)
pt = top_n_list('pt', 1e5, wordlist='large')
zh = top_n_list('zh', 1e5)
#---------------------------------------------------------------
arPopular = open(dest + '/arPopular.txt', 'w')
arLongTail = open(dest + '/arLongTail.txt', 'w')
integral100 = 0
for i in range(len(ar)):
integral100 += word_frequency(ar[i], 'ar')
integral80 = 0
for i in range(len(ar)):
integral80 += word_frequency(ar[i], 'ar')
if (integral80 <= 0.80*integral100):from wordfreq import word_frequency
from wordfreq import zipf_frequency
from wordfreq import top_n_list
import matplotlib.pyplot as plt
dest = "../src/org/owasp/passfault/wordlists/"
de = top_n_list('de', 1e5, wordlist='large')
en = top_n_list('en', 1e5, wordlist='large')
es = top_n_list('es', 1e5, wordlist='large')
fr = top_n_list('fr', 1e5, wordlist='large')
it = top_n_list('it', 1e5, wordlist='large')
nl = top_n_list('nl', 1e5, wordlist='large')
pt = top_n_list('pt', 1e5, wordlist='large')
#---------------------------------------------------------------
dePopular = open(dest + '/dePopular.words', 'w')
deLongTail = open(dest + '/deLongTail.words', 'w')
integral100 = 0
for i in range(len(de)):
integral100 += word_frequency(de[i], 'de', wordlist='large')
print(integral100)
integral80 = 0#Written by Bernardo Rodrigues (bernardoaraujor@gmail.com)
#Based on Luminoso Insight's wordfreq module (https://github.com/LuminosoInsight/wordfreq/)
from wordfreq import word_frequency
from wordfreq import zipf_frequency
from wordfreq import top_n_list
#import matplotlib.pyplot as plt
dest = "./wordlists/"
ar = top_n_list('ar', 1e5, wordlist='large')
de = top_n_list('de', 1e5, wordlist='large')
en = top_n_list('en', 1e5, wordlist='large')
es = top_n_list('es', 1e5, wordlist='large')
fi = top_n_list('fi', 1e5)
fr = top_n_list('fr', 1e5, wordlist='large')
hi = top_n_list('hi', 1e5)
it = top_n_list('it', 1e5, wordlist='large')
ja = top_n_list('ja', 1e5)
nl = top_n_list('nl', 1e5, wordlist='large')
sv = top_n_list('sv', 1e5)
pt = top_n_list('pt', 1e5, wordlist='large')
zh = top_n_list('zh', 1e5)
#---------------------------------------------------------------
arPopular = open(dest + '/arPopular.txt', 'w')
arLongTail = open(dest + '/arLongTail.txt', 'w')
integral100 = 0
for i in range(len(ar)):
integral100 += word_frequency(ar[i], 'ar')wordfreq
Look up the frequencies of words in many languages, based on many sources of data.
Package Health Score
56 / 100Popular wordfreq functions
- wordfreq.available_languages
- wordfreq.cB_to_freq
- wordfreq.config
- wordfreq.config.DB_FILENAME
- wordfreq.config.RAW_DATA_DIR
- wordfreq.get_frequency_dict
- wordfreq.iter_wordlist
- wordfreq.language_info.get_language_info
- wordfreq.lossy_tokenize
- wordfreq.preprocess.preprocess_text
- wordfreq.print_wordfreq
- wordfreq.simple_tokenize
- wordfreq.TOKEN_RE.search
- wordfreq.tokenize
- wordfreq.tokens.lossy_tokenize
- wordfreq.top_n_list
- wordfreq.util.standardize_word
- wordfreq.word_frequency
- wordfreq.wordfreq
- wordfreq.zipf_frequency